| { | |
| "best_metric": 8.905207633972168, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03555634569657103, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007111269139314207, | |
| "grad_norm": 4.391914367675781, | |
| "learning_rate": 5e-05, | |
| "loss": 10.2843, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007111269139314207, | |
| "eval_loss": 10.709673881530762, | |
| "eval_runtime": 0.4892, | |
| "eval_samples_per_second": 102.216, | |
| "eval_steps_per_second": 26.576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014222538278628415, | |
| "grad_norm": 4.697262763977051, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4354, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002133380741794262, | |
| "grad_norm": 4.8142218589782715, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.5401, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002844507655725683, | |
| "grad_norm": 4.4203386306762695, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.6847, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0035556345696571034, | |
| "grad_norm": 4.616575717926025, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.5382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004266761483588524, | |
| "grad_norm": 4.453695297241211, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.493, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004977888397519945, | |
| "grad_norm": 4.64595365524292, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.4906, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005689015311451366, | |
| "grad_norm": 4.16403341293335, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.208, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006400142225382786, | |
| "grad_norm": 4.626234531402588, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3911, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007111269139314207, | |
| "grad_norm": 4.048719882965088, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007822396053245627, | |
| "grad_norm": 4.476191997528076, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.4335, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008533522967177049, | |
| "grad_norm": 4.421826362609863, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.2073, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00924464988110847, | |
| "grad_norm": 3.3022351264953613, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.3604, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00995577679503989, | |
| "grad_norm": 3.388110399246216, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 9.4965, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01066690370897131, | |
| "grad_norm": 3.273960590362549, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.4797, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011378030622902732, | |
| "grad_norm": 3.3199994564056396, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.495, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012089157536834151, | |
| "grad_norm": 3.0522372722625732, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.6073, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012800284450765573, | |
| "grad_norm": 2.893317222595215, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.8366, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013511411364696994, | |
| "grad_norm": 2.8836116790771484, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.3707, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014222538278628414, | |
| "grad_norm": 2.862773895263672, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.4298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014933665192559835, | |
| "grad_norm": 2.72392201423645, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.7437, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015644792106491254, | |
| "grad_norm": 2.617037534713745, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.5262, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.016355919020422677, | |
| "grad_norm": 2.5886077880859375, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.6284, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017067045934354097, | |
| "grad_norm": 2.6617650985717773, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.7558, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017778172848285517, | |
| "grad_norm": 2.827671766281128, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.7337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017778172848285517, | |
| "eval_loss": 9.181326866149902, | |
| "eval_runtime": 0.4688, | |
| "eval_samples_per_second": 106.656, | |
| "eval_steps_per_second": 27.731, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01848929976221694, | |
| "grad_norm": 2.6871771812438965, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 8.7595, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01920042667614836, | |
| "grad_norm": 2.3026132583618164, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.0285, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01991155359007978, | |
| "grad_norm": 2.0922391414642334, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 9.0976, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0206226805040112, | |
| "grad_norm": 2.124882936477661, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 9.0691, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02133380741794262, | |
| "grad_norm": 2.0727596282958984, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 9.2239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02204493433187404, | |
| "grad_norm": 1.893613576889038, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 9.3525, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.022756061245805464, | |
| "grad_norm": 1.9661246538162231, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 9.2901, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.023467188159736883, | |
| "grad_norm": 1.8640170097351074, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.332, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.024178315073668303, | |
| "grad_norm": 1.9543989896774292, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.3554, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024889441987599726, | |
| "grad_norm": 1.9747636318206787, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 9.4425, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025600568901531146, | |
| "grad_norm": 2.04024600982666, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 9.7109, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.026311695815462565, | |
| "grad_norm": 2.1174285411834717, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 9.3722, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.027022822729393988, | |
| "grad_norm": 1.8444091081619263, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 8.786, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.027733949643325408, | |
| "grad_norm": 1.920892596244812, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 8.958, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.028445076557256827, | |
| "grad_norm": 1.868925929069519, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 8.7157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02915620347118825, | |
| "grad_norm": 1.63834547996521, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 8.9606, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02986733038511967, | |
| "grad_norm": 1.5350797176361084, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.0381, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03057845729905109, | |
| "grad_norm": 1.5533965826034546, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 9.0667, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03128958421298251, | |
| "grad_norm": 1.6352142095565796, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 9.1235, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03200071112691393, | |
| "grad_norm": 1.6297922134399414, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 9.1851, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.032711838040845355, | |
| "grad_norm": 1.6186994314193726, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 9.4025, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03342296495477677, | |
| "grad_norm": 1.5999581813812256, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 9.324, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.034134091868708194, | |
| "grad_norm": 1.7737746238708496, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 9.326, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03484521878263962, | |
| "grad_norm": 1.9884766340255737, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 9.4523, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03555634569657103, | |
| "grad_norm": 2.1337687969207764, | |
| "learning_rate": 1e-05, | |
| "loss": 9.5157, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03555634569657103, | |
| "eval_loss": 8.905207633972168, | |
| "eval_runtime": 0.4716, | |
| "eval_samples_per_second": 106.032, | |
| "eval_steps_per_second": 27.568, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 232013797785600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |